Skip to search formSkip to main contentSkip to account menu
You are currently offline. Some features of the site may not work correctly.

MNIST database

Known as: MNIST, MNIST dataset 
The MNIST database (Mixed National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used… 
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2017
Highly Cited
2017
The MNIST dataset has become a standard benchmark for learning, classification and computer vision systems. Contributing to its… 
  • table I
  • figure 1
  • table II
  • figure 2
  • figure 3
Highly Cited
2017
Highly Cited
2017
The MNIST dataset has become a standard benchmark for learning, classification and computer vision systems. Contributing to its… 
  • table I
  • figure 1
  • table II
  • figure 2
  • figure 3
Highly Cited
2016
Highly Cited
2016
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks… 
  • figure 1
  • figure 2
  • figure 3
  • table 1
  • table 2
Highly Cited
2015
Highly Cited
2015
Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by… 
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Highly Cited
2015
Highly Cited
2015
A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the… 
  • table 1
  • table 2
  • table 3
  • table 4
  • table 5
Highly Cited
2014
Highly Cited
2014
Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the… 
  • figure 1
  • table 1
  • figure 2
  • table 2
Highly Cited
2012
Highly Cited
2012
  • L. Deng
  • IEEE Signal Processing Magazine
  • 2012
  • Corpus ID: 5280072
In this issue, “Best of the Web” presents the modified National Institute of Standards and Technology (MNIST) resources… 
Highly Cited
2012
Highly Cited
2012
We present a novel per-dimension learning rate method for gradient descent called ADADELTA. The method dynamically adapts over… 
  • figure 1
  • table 1
  • table 2
  • figure 2
  • figure 3
Highly Cited
2005
Highly Cited
2005
Disclosed is an improved articulated bar flail having shearing edges for efficiently shredding materials. An improved shredder… 
Highly Cited
2004
Highly Cited
2004
Abstract We have developed a novel neural classifier LImited Receptive Area (LIRA) for the image recognition. The classifier LIRA… 
  • table 1
  • figure 1
  • figure 3
  • figure 4
  • table 2